There is a large interest in Artificial Intelligence (AI) in the Life Science field and the potential for analysis of complex biological data using AI-based methods is in principle unlimited. Advanced Therapy Medical Products (ATMP) are therapies that now rapidly are developing and that can greatly benefit from the revolution in the development of AI. This project will develop and implement a deep learning (DL) method for quality control (QC) analysis. The method will be developed as a platform that can be used for all types of cells and for the development of the method human embryonic stem cells (hESCs) will be used as a model system to stepwise develop a neural network (NN) for the classification of cell quality, using quantitative PCR data (qPCR). The innovation and uniqueness of this project reside in two main aspects. Interpretation of neural networks and transfer learning across technologies. The interpretation of the representations learned in the initial NN classifier developed using single-cell RNA-seq data will allow the identification of transcriptomic signatures associated with cell quality. The knowledge contained in the NN classifier will be transferred to a reduced NN classifier that will use qPCR-based data as input. The advantage of this is that qPCR data is cost-effective to generate and therefore suitable for implementation in an industrial QC system. The panel of biomarkers that have been identified by the model will be commercialized as qPCR assays, and the analysis method will be integrated as a package in commercial software for advanced qPCR analyses.